From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:43956) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ebGdt-0005TG-BI for qemu-devel@nongnu.org; Mon, 15 Jan 2018 21:06:28 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ebGdq-0007ch-6Z for qemu-devel@nongnu.org; Mon, 15 Jan 2018 21:06:25 -0500 Received: from mx1.redhat.com ([209.132.183.28]:58478) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1ebGdp-0007bw-VI for qemu-devel@nongnu.org; Mon, 15 Jan 2018 21:06:22 -0500 Date: Tue, 16 Jan 2018 04:06:12 +0200 From: "Michael S. Tsirkin" Message-ID: <20180116040030-mutt-send-email-mst@kernel.org> References: <20180114090147.39255-1-marcel@redhat.com> <20180114090147.39255-4-marcel@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20180114090147.39255-4-marcel@redhat.com> Subject: Re: [Qemu-devel] [PATCH V7 3/5] docs: add pvrdma device documentation. List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Marcel Apfelbaum Cc: qemu-devel@nongnu.org, ehabkost@redhat.com, imammedo@redhat.com, yuval.shaia@oracle.com, pbonzini@redhat.com, borntraeger@de.ibm.com, cohuck@redhat.com, f4bug@amsat.org On Sun, Jan 14, 2018 at 11:01:45AM +0200, Marcel Apfelbaum wrote: > +5. Limitations > +============== Limitations are fine but need to cause init failures since users don't poke in the internal documentation. > +- The device obviously is limited by the Guest Linux Driver features implementation > + of the VMware device API. > +- Memory registration mechanism requires mremap for every page in the buffer in order > + to map it to a contiguous virtual address range. Since this is not the data path > + it should not matter much. Depends on the size of the region I guess. Did you try this with several gigabytes of memory? If we are talking seconds of downtime, it's worth documenting so people aren't surprised. Alternatively, limit the max size of MR? > +- The device requires target page size to be the same as the host page size. Pls add code to fail init when this is not the case. > +- QEMU cannot map guest RAM from a file descriptor if a pvrdma device is attached, > + so it can't work with huge pages. The limitation will be addressed in the future, > + however QEMU allocates Guest RAM with MADV_HUGEPAGE so if there are enough huge > + pages available, QEMU will use them. Same here. > +- As previously stated, migration is not supported yet, however with some hardware > + support can be done. I don't see a migration blocker. -- MST